FastOPD: On-Policy Distillation for Lightweight VLA Deployment
- 类型:arxiv
- 标识:2610.02832
- 链接:https://arxiv.org/abs/2610.02832
- 主分类:multimodal
- 形态:application
- TLDR:Vision-Language-Action (VLA) foundation models have scaled rapidly to enhance manipulation performance and generalizability, but this scaling incurs high computational costs that render real-world deployment increasingly challenging. Existing approaches typically mitigate this issue by designing smaller architectures or reducing the iterative denoising steps in flow-based policies. In this work, we propose FastOPD, a foundation-to-lightweight VLA framework that enables the practical deployment of large-scale VLAs through efficient on-policy distillation. Specifically, FastOPD adapts a flow map
- 副分类:engineering
- 待LLM分类:否
- 标题中文:FastOPD:面向轻量 VLA 部署的在线蒸馏
- TLDR中文:视觉-语言-动作(VLA)基础模型规模迅速扩大以提升操作性能与泛化能力,但这种规模化带来了高昂的计算成本,使真实世界部署日益困难。现有方法通常通过设计更小的架构或减少基于流(flow-based)策略中的迭代去噪步数来缓解该问题。本文提出 FastOPD,一个从基础到轻量的 VLA 框架,通过高效的在线蒸馏实现大规模 VLA 的实际部署。具体而言,FastOPD 适配流映射(flow map)……
- 来源文件:
- /inbox/tom/_candidates/2026-10-08-agent-rag-longcontext-candidates.json